A new study from Anthropic introduces "persona vectors," a technique for developers to monitor, predict and control unwanted LLM behaviors.

I’ve chatted with enough bots to know when something feels a little off. Sometimes, they’re overly flattering. Other times, ...

Last week, Anthropic presented some research into how AI “personalities” work. That is, how their tone, responses, and ...

In the paper, Anthropic explained that it can steer these vectors by instructing models to act in certain ways -- for example ...